{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5374,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018608113137327874,
      "grad_norm": 0.15951524674892426,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.4521,
      "step": 100
    },
    {
      "epoch": 0.03721622627465575,
      "grad_norm": 0.10372528433799744,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.4034,
      "step": 200
    },
    {
      "epoch": 0.05582433941198362,
      "grad_norm": 0.20789675414562225,
      "learning_rate": 6e-06,
      "loss": 2.4476,
      "step": 300
    },
    {
      "epoch": 0.0744324525493115,
      "grad_norm": 0.2809026539325714,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.4063,
      "step": 400
    },
    {
      "epoch": 0.09304056568663938,
      "grad_norm": 0.3346979320049286,
      "learning_rate": 1e-05,
      "loss": 2.3631,
      "step": 500
    },
    {
      "epoch": 0.11164867882396724,
      "grad_norm": 0.42336997389793396,
      "learning_rate": 1.2e-05,
      "loss": 2.3173,
      "step": 600
    },
    {
      "epoch": 0.13025679196129514,
      "grad_norm": 0.4591374099254608,
      "learning_rate": 1.4e-05,
      "loss": 2.2564,
      "step": 700
    },
    {
      "epoch": 0.148864905098623,
      "grad_norm": 0.5659797787666321,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.273,
      "step": 800
    },
    {
      "epoch": 0.16747301823595087,
      "grad_norm": 0.5892286896705627,
      "learning_rate": 1.8e-05,
      "loss": 2.2587,
      "step": 900
    },
    {
      "epoch": 0.18608113137327875,
      "grad_norm": 0.5323100686073303,
      "learning_rate": 2e-05,
      "loss": 2.1991,
      "step": 1000
    },
    {
      "epoch": 0.20468924451060663,
      "grad_norm": 0.6430222988128662,
      "learning_rate": 1.9974217472841614e-05,
      "loss": 2.1777,
      "step": 1100
    },
    {
      "epoch": 0.22329735764793449,
      "grad_norm": 0.6999238133430481,
      "learning_rate": 1.9897002839107783e-05,
      "loss": 2.1297,
      "step": 1200
    },
    {
      "epoch": 0.24190547078526237,
      "grad_norm": 0.8810726404190063,
      "learning_rate": 1.9768754256476755e-05,
      "loss": 2.17,
      "step": 1300
    },
    {
      "epoch": 0.2605135839225903,
      "grad_norm": 0.8605418801307678,
      "learning_rate": 1.9590133039461487e-05,
      "loss": 2.13,
      "step": 1400
    },
    {
      "epoch": 0.27912169705991813,
      "grad_norm": 0.711585521697998,
      "learning_rate": 1.936206024933772e-05,
      "loss": 2.162,
      "step": 1500
    },
    {
      "epoch": 0.297729810197246,
      "grad_norm": 0.8360315561294556,
      "learning_rate": 1.908571194468655e-05,
      "loss": 2.165,
      "step": 1600
    },
    {
      "epoch": 0.3163379233345739,
      "grad_norm": 0.9491225481033325,
      "learning_rate": 1.8762513117041943e-05,
      "loss": 2.0905,
      "step": 1700
    },
    {
      "epoch": 0.33494603647190174,
      "grad_norm": 0.6673754453659058,
      "learning_rate": 1.839413034291416e-05,
      "loss": 2.1022,
      "step": 1800
    },
    {
      "epoch": 0.35355414960922965,
      "grad_norm": 0.8447780013084412,
      "learning_rate": 1.7982463190078928e-05,
      "loss": 2.1088,
      "step": 1900
    },
    {
      "epoch": 0.3721622627465575,
      "grad_norm": 0.758438229560852,
      "learning_rate": 1.752963442244589e-05,
      "loss": 2.1265,
      "step": 2000
    },
    {
      "epoch": 0.39077037588388536,
      "grad_norm": 1.1905587911605835,
      "learning_rate": 1.703797905401496e-05,
      "loss": 2.0621,
      "step": 2100
    },
    {
      "epoch": 0.40937848902121327,
      "grad_norm": 0.8596579432487488,
      "learning_rate": 1.6510032308363964e-05,
      "loss": 2.0768,
      "step": 2200
    },
    {
      "epoch": 0.4279866021585411,
      "grad_norm": 0.8008110523223877,
      "learning_rate": 1.5948516545754497e-05,
      "loss": 2.134,
      "step": 2300
    },
    {
      "epoch": 0.44659471529586897,
      "grad_norm": 0.7902112007141113,
      "learning_rate": 1.5356327225266418e-05,
      "loss": 2.0793,
      "step": 2400
    },
    {
      "epoch": 0.4652028284331969,
      "grad_norm": 1.021168828010559,
      "learning_rate": 1.4736517974347408e-05,
      "loss": 2.0917,
      "step": 2500
    },
    {
      "epoch": 0.48381094157052473,
      "grad_norm": 1.0414773225784302,
      "learning_rate": 1.4092284842766439e-05,
      "loss": 2.0306,
      "step": 2600
    },
    {
      "epoch": 0.5024190547078526,
      "grad_norm": 0.8652853965759277,
      "learning_rate": 1.3426949822165768e-05,
      "loss": 2.0742,
      "step": 2700
    },
    {
      "epoch": 0.5210271678451805,
      "grad_norm": 0.8237012624740601,
      "learning_rate": 1.2743943716193017e-05,
      "loss": 2.0428,
      "step": 2800
    },
    {
      "epoch": 0.5396352809825083,
      "grad_norm": 1.091333270072937,
      "learning_rate": 1.2046788449543496e-05,
      "loss": 2.0632,
      "step": 2900
    },
    {
      "epoch": 0.5582433941198363,
      "grad_norm": 0.9181482791900635,
      "learning_rate": 1.1339078907136409e-05,
      "loss": 1.9869,
      "step": 3000
    },
    {
      "epoch": 0.5768515072571642,
      "grad_norm": 1.1163825988769531,
      "learning_rate": 1.0624464397071229e-05,
      "loss": 2.0724,
      "step": 3100
    },
    {
      "epoch": 0.595459620394492,
      "grad_norm": 1.086317539215088,
      "learning_rate": 9.906629832950659e-06,
      "loss": 2.0576,
      "step": 3200
    },
    {
      "epoch": 0.6140677335318199,
      "grad_norm": 0.822471559047699,
      "learning_rate": 9.189276732603637e-06,
      "loss": 2.1059,
      "step": 3300
    },
    {
      "epoch": 0.6326758466691478,
      "grad_norm": 0.9485145807266235,
      "learning_rate": 8.47610413118853e-06,
      "loss": 2.0566,
      "step": 3400
    },
    {
      "epoch": 0.6512839598064756,
      "grad_norm": 0.9303804039955139,
      "learning_rate": 7.770789507098263e-06,
      "loss": 2.0242,
      "step": 3500
    },
    {
      "epoch": 0.6698920729438035,
      "grad_norm": 1.1080023050308228,
      "learning_rate": 7.076969819022999e-06,
      "loss": 1.9736,
      "step": 3600
    },
    {
      "epoch": 0.6885001860811314,
      "grad_norm": 1.0893449783325195,
      "learning_rate": 6.3982227519528986e-06,
      "loss": 2.0214,
      "step": 3700
    },
    {
      "epoch": 0.7071082992184593,
      "grad_norm": 0.9729887843132019,
      "learning_rate": 5.738048268826046e-06,
      "loss": 2.0238,
      "step": 3800
    },
    {
      "epoch": 0.7257164123557871,
      "grad_norm": 0.7429510951042175,
      "learning_rate": 5.099850562950539e-06,
      "loss": 2.0608,
      "step": 3900
    },
    {
      "epoch": 0.744324525493115,
      "grad_norm": 1.201204538345337,
      "learning_rate": 4.486920504263212e-06,
      "loss": 1.9825,
      "step": 4000
    },
    {
      "epoch": 0.7629326386304429,
      "grad_norm": 0.9092488884925842,
      "learning_rate": 3.902418669940925e-06,
      "loss": 2.0295,
      "step": 4100
    },
    {
      "epoch": 0.7815407517677707,
      "grad_norm": 1.1268125772476196,
      "learning_rate": 3.3493590468671868e-06,
      "loss": 2.029,
      "step": 4200
    },
    {
      "epoch": 0.8001488649050986,
      "grad_norm": 0.817008376121521,
      "learning_rate": 2.8305934899924135e-06,
      "loss": 2.0129,
      "step": 4300
    },
    {
      "epoch": 0.8187569780424265,
      "grad_norm": 0.9579901099205017,
      "learning_rate": 2.348797016728398e-06,
      "loss": 2.0472,
      "step": 4400
    },
    {
      "epoch": 0.8373650911797543,
      "grad_norm": 0.8800289034843445,
      "learning_rate": 1.9064540132064946e-06,
      "loss": 1.959,
      "step": 4500
    },
    {
      "epoch": 0.8559732043170822,
      "grad_norm": 0.9605334997177124,
      "learning_rate": 1.505845423527027e-06,
      "loss": 1.9486,
      "step": 4600
    },
    {
      "epoch": 0.8745813174544101,
      "grad_norm": 0.7564200162887573,
      "learning_rate": 1.1490369880586516e-06,
      "loss": 2.0324,
      "step": 4700
    },
    {
      "epoch": 0.8931894305917379,
      "grad_norm": 1.0660285949707031,
      "learning_rate": 8.378685914369323e-07,
      "loss": 2.0176,
      "step": 4800
    },
    {
      "epoch": 0.9117975437290659,
      "grad_norm": 1.1286784410476685,
      "learning_rate": 5.739447751892135e-07,
      "loss": 2.0409,
      "step": 4900
    },
    {
      "epoch": 0.9304056568663938,
      "grad_norm": 0.9878057241439819,
      "learning_rate": 3.586264639075265e-07,
      "loss": 1.967,
      "step": 5000
    },
    {
      "epoch": 0.9490137700037217,
      "grad_norm": 0.9573999643325806,
      "learning_rate": 1.9302394763353606e-07,
      "loss": 2.0823,
      "step": 5100
    },
    {
      "epoch": 0.9676218831410495,
      "grad_norm": 0.7985095381736755,
      "learning_rate": 7.79911566419056e-08,
      "loss": 2.0383,
      "step": 5200
    },
    {
      "epoch": 0.9862299962783774,
      "grad_norm": 1.0881154537200928,
      "learning_rate": 1.4121258144207395e-08,
      "loss": 2.0119,
      "step": 5300
    },
    {
      "epoch": 1.0,
      "step": 5374,
      "total_flos": 9.788605661184e+16,
      "train_loss": 2.1113919824927456,
      "train_runtime": 862.752,
      "train_samples_per_second": 12.458,
      "train_steps_per_second": 6.229
    }
  ],
  "logging_steps": 100,
  "max_steps": 5374,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.788605661184e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}